首页 | 本学科首页   官方微博 | 高级检索  
     检索      

采用图像定位与轮廓检测的喷墨宽度测量算法
引用本文:兰伟,,何松柏.采用图像定位与轮廓检测的喷墨宽度测量算法[J].华侨大学学报(自然科学版),2017,0(3):402-407.
作者姓名:兰伟    何松柏
作者单位:1. 重庆城市职业学院 信息工程系, 重庆 402160;2. 电子科技大学 电子工程学院, 四川 成都 610000
摘    要:提出基于图像定位与轮廓检测的喷墨宽度测量算法.首先,根据图像灰度熵特征与旋转定位函数,提出基于动态阈值熵函数分割与EmguCV的产品定位算子,得到产品中心点坐标与旋转角度;然后,传递给机器人Robert,引导Robert到产品边缘喷墨上方进行局部图像采集;最后,采用大律法分割法处理喷墨边缘图像,设计基于Canny边缘检测与轮廓检测的测量算子,从而完成喷墨宽度测量.实验数据显示:与当前目标宽度测量技术相比,文中算法具有更高的测量精度与稳定性.

关 键 词:喷墨宽度  图像定位  轮廓检测  动态阈值熵函数  边缘检测

Measurement Algorithm of Inking Width Using Image Localization and Contour Detection
LAN Wei,' target="_blank" rel="external">,HE Songbo.Measurement Algorithm of Inking Width Using Image Localization and Contour Detection[J].Journal of Huaqiao University(Natural Science),2017,0(3):402-407.
Authors:LAN Wei  " target="_blank">' target="_blank" rel="external">  HE Songbo
Institution:1. Department of Information Engineering, Chongqing City Vocational College, Chongqing 402160, China; 2. College of Electronic Engineering, University of Electronic Science and Technology of China, Chengdu 610000, China
Abstract:This paper proposed a new measurement algorithm of inking width based on image localization and contour detection. Firstly, product location algorithm which’s based on segmentation of dynamic threshold value entropy function and EmguCV was proposed to get product center coordinates and rotation angle, and then passed it to the Robert, and guide the Robert to the local image acquisition edge to command inkjet products. Finally, great law segmentation was adopted to process the image on inkjet edge, based on Canny edge detection and contour measurement operator to complete inkjet width measurement. Experimental data shows that: compared with the current measurement technology, this algorithm has higher precision and stability..
Keywords:inkjet width  image localization  contour detection  dynamic threshold entropy function  edge detection
本文献已被 CNKI 等数据库收录!
点击此处可从《华侨大学学报(自然科学版)》浏览原始摘要信息
点击此处可从《华侨大学学报(自然科学版)》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号